feat(doc): 优化 rapidocr
This commit is contained in:
Wenjie Zhang
parent
86f92f7f3f
commit
d9d7ec1c11
@ -1,4 +1,3 @@
|
||||
MODEL_DIR=./models
|
||||
SAVE_DIR=./saves
|
||||
|
||||
# region model_provider
|
||||
|
||||
@ -49,6 +49,7 @@ dependencies = [
|
||||
"networkx>=3.5",
|
||||
"openai>=1.109",
|
||||
"opencv-python-headless>=4.11.0.86",
|
||||
"onnxruntime>=1.20.0",
|
||||
"Pillow>=10.5.0",
|
||||
"psycopg[binary,pool]>=3.3.3",
|
||||
"pyjwt>=2.8.0",
|
||||
@ -60,7 +61,7 @@ dependencies = [
|
||||
"python-jose[cryptography]>=3.4.0",
|
||||
"python-multipart>=0.0.20",
|
||||
"pyyaml>=6.0.2",
|
||||
"rapidocr-onnxruntime>=1.4.4",
|
||||
"rapidocr>=3.0.0",
|
||||
"readability-lxml>=0.8.1",
|
||||
"redis>=5.2.0",
|
||||
"rich>=13.7.1",
|
||||
|
||||
@ -1,7 +1,7 @@
|
||||
"""
|
||||
RapidOCR 解析器 - 纯OCR文字识别
|
||||
|
||||
使用 RapidOCR (PP-OCRv4) 进行文字识别
|
||||
使用 RapidOCR (PP-OCRv5) 进行文字识别
|
||||
"""
|
||||
|
||||
import os
|
||||
@ -12,7 +12,7 @@ from pathlib import Path
|
||||
import fitz
|
||||
import numpy as np
|
||||
from PIL import Image
|
||||
from rapidocr_onnxruntime import RapidOCR
|
||||
from rapidocr import EngineType, LangDet, LangRec, ModelType, OCRVersion, RapidOCR
|
||||
|
||||
from yuxi.plugins.parser.base import BaseDocumentProcessor, OCRException
|
||||
from yuxi.utils import logger
|
||||
@ -24,9 +24,6 @@ class RapidOCRParser(BaseDocumentProcessor):
|
||||
def __init__(self, det_box_thresh: float = 0.3):
|
||||
self.ocr = None
|
||||
self.det_box_thresh = det_box_thresh
|
||||
self.model_dir_root = (
|
||||
os.getenv("MODEL_DIR") if not os.getenv("RUNNING_IN_DOCKER") else os.getenv("MODEL_DIR_IN_DOCKER")
|
||||
)
|
||||
|
||||
def get_service_name(self) -> str:
|
||||
return "rapid_ocr"
|
||||
@ -34,49 +31,32 @@ class RapidOCRParser(BaseDocumentProcessor):
|
||||
def get_supported_extensions(self) -> list[str]:
|
||||
return [".pdf", ".jpg", ".jpeg", ".png", ".bmp", ".tiff", ".tif"]
|
||||
|
||||
def _get_model_paths(self) -> tuple[str, str]:
|
||||
"""获取模型文件路径"""
|
||||
model_dir = os.path.join(self.model_dir_root, "SWHL/RapidOCR")
|
||||
det_model_path = os.path.join(model_dir, "PP-OCRv4/ch_PP-OCRv4_det_infer.onnx")
|
||||
rec_model_path = os.path.join(model_dir, "PP-OCRv4/ch_PP-OCRv4_rec_infer.onnx")
|
||||
return det_model_path, rec_model_path
|
||||
def _get_model_params(self) -> dict[str, object]:
|
||||
return {
|
||||
"Det.engine_type": EngineType.ONNXRUNTIME,
|
||||
"Det.lang_type": LangDet.CH,
|
||||
"Det.model_type": ModelType.MOBILE,
|
||||
"Det.ocr_version": OCRVersion.PPOCRV5,
|
||||
"Det.box_thresh": self.det_box_thresh,
|
||||
"Cls.engine_type": EngineType.ONNXRUNTIME,
|
||||
"Rec.engine_type": EngineType.ONNXRUNTIME,
|
||||
"Rec.lang_type": LangRec.CH,
|
||||
"Rec.model_type": ModelType.MOBILE,
|
||||
"Rec.ocr_version": OCRVersion.PPOCRV5,
|
||||
}
|
||||
|
||||
def check_health(self) -> dict:
|
||||
"""检查 RapidOCR 模型是否可用"""
|
||||
try:
|
||||
det_model_path, rec_model_path = self._get_model_paths()
|
||||
model_dir = os.path.dirname(os.path.dirname(det_model_path))
|
||||
|
||||
if not os.path.exists(model_dir):
|
||||
return {
|
||||
"status": "unavailable",
|
||||
"message": f"模型目录不存在: {model_dir}",
|
||||
"details": {"model_dir": model_dir},
|
||||
}
|
||||
|
||||
if not os.path.exists(det_model_path) or not os.path.exists(rec_model_path):
|
||||
return {
|
||||
"status": "unavailable",
|
||||
"message": "模型文件缺失",
|
||||
"details": {"det_model": det_model_path, "rec_model": rec_model_path},
|
||||
}
|
||||
|
||||
# 尝试加载模型
|
||||
try:
|
||||
test_ocr = RapidOCR(
|
||||
det_box_thresh=self.det_box_thresh, det_model_path=det_model_path, rec_model_path=rec_model_path
|
||||
)
|
||||
del test_ocr # 释放资源
|
||||
return {
|
||||
"status": "healthy",
|
||||
"message": "RapidOCR模型可用",
|
||||
"details": {"model_path": self._get_model_paths()},
|
||||
}
|
||||
except Exception as e:
|
||||
return {"status": "error", "message": f"模型加载失败: {str(e)}", "details": {"error": str(e)}}
|
||||
|
||||
test_ocr = RapidOCR(params=self._get_model_params())
|
||||
del test_ocr
|
||||
return {
|
||||
"status": "healthy",
|
||||
"message": "RapidOCR PP-OCRv5 模型可用",
|
||||
"details": {"ocr_version": "PP-OCRv5", "engine": "onnxruntime"},
|
||||
}
|
||||
except Exception as e:
|
||||
return {"status": "error", "message": f"健康检查失败: {str(e)}", "details": {"error": str(e)}}
|
||||
return {"status": "error", "message": f"模型加载失败: {str(e)}", "details": {"error": str(e)}}
|
||||
|
||||
def _load_model(self):
|
||||
"""延迟加载 OCR 模型"""
|
||||
@ -85,17 +65,9 @@ class RapidOCRParser(BaseDocumentProcessor):
|
||||
|
||||
logger.info("加载 RapidOCR 模型...")
|
||||
|
||||
# 先检查健康状态
|
||||
health = self.check_health()
|
||||
if health["status"] != "healthy":
|
||||
raise OCRException(health["message"], self.get_service_name(), health["status"])
|
||||
|
||||
try:
|
||||
det_model_path, rec_model_path = self._get_model_paths()
|
||||
self.ocr = RapidOCR(
|
||||
det_box_thresh=self.det_box_thresh, det_model_path=det_model_path, rec_model_path=rec_model_path
|
||||
)
|
||||
logger.info(f"RapidOCR 模型加载成功 (det_box_thresh={self.det_box_thresh})")
|
||||
self.ocr = RapidOCR(params=self._get_model_params())
|
||||
logger.info(f"RapidOCR PP-OCRv5 模型加载成功 (det_box_thresh={self.det_box_thresh})")
|
||||
except Exception as e:
|
||||
raise OCRException(f"RapidOCR模型加载失败: {str(e)}", self.get_service_name(), "load_failed")
|
||||
|
||||
@ -128,12 +100,12 @@ class RapidOCRParser(BaseDocumentProcessor):
|
||||
try:
|
||||
# 执行 OCR
|
||||
start_time = time.time()
|
||||
result, _ = self.ocr(image_path)
|
||||
result = self.ocr(image_path)
|
||||
processing_time = time.time() - start_time
|
||||
|
||||
# 提取文本
|
||||
if result:
|
||||
text = "\n".join([line[1] for line in result])
|
||||
if result.txts:
|
||||
text = "\n".join(result.txts)
|
||||
logger.info(
|
||||
f"RapidOCR 成功: {os.path.basename(image_path) if isinstance(image, str) else 'temp_image'}"
|
||||
f" ({processing_time:.2f}s)"
|
||||
|
||||
108
backend/uv.lock
108
backend/uv.lock
@ -2861,28 +2861,27 @@ wheels = [
|
||||
|
||||
[[package]]
|
||||
name = "onnxruntime"
|
||||
version = "1.24.4"
|
||||
version = "1.26.0"
|
||||
source = { registry = "https://pypi.tuna.tsinghua.edu.cn/simple" }
|
||||
dependencies = [
|
||||
{ name = "flatbuffers" },
|
||||
{ name = "numpy" },
|
||||
{ name = "packaging" },
|
||||
{ name = "protobuf" },
|
||||
{ name = "sympy" },
|
||||
]
|
||||
wheels = [
|
||||
{ url = "https://pypi.tuna.tsinghua.edu.cn/packages/d7/38/31db1b232b4ba960065a90c1506ad7a56995cd8482033184e97fadca17cc/onnxruntime-1.24.4-cp312-cp312-macosx_14_0_arm64.whl", hash = "sha256:cad1c2b3f455c55678ab2a8caa51fb420c25e6e3cf10f4c23653cdabedc8de78", size = 17341875, upload-time = "2026-03-17T22:05:51.669Z" },
|
||||
{ url = "https://pypi.tuna.tsinghua.edu.cn/packages/aa/60/c4d1c8043eb42f8a9aa9e931c8c293d289c48ff463267130eca97d13357f/onnxruntime-1.24.4-cp312-cp312-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:1a5c5a544b22f90859c88617ecb30e161ee3349fcc73878854f43d77f00558b5", size = 15172485, upload-time = "2026-03-17T22:03:32.182Z" },
|
||||
{ url = "https://pypi.tuna.tsinghua.edu.cn/packages/6d/ab/5b68110e0460d73fad814d5bd11c7b1ddcce5c37b10177eb264d6a36e331/onnxruntime-1.24.4-cp312-cp312-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:0d640eb9f3782689b55cfa715094474cd5662f2f137be6a6f847a594b6e9705c", size = 17244912, upload-time = "2026-03-17T22:04:37.251Z" },
|
||||
{ url = "https://pypi.tuna.tsinghua.edu.cn/packages/8b/f4/6b89e297b93704345f0f3f8c62229bee323ef25682a3f9b4f89a39324950/onnxruntime-1.24.4-cp312-cp312-win_amd64.whl", hash = "sha256:535b29475ca42b593c45fbb2152fbf1cdf3f287315bf650e6a724a0a1d065cdb", size = 12596856, upload-time = "2026-03-17T22:05:41.224Z" },
|
||||
{ url = "https://pypi.tuna.tsinghua.edu.cn/packages/43/06/8b8ec6e9e6a474fcd5d772453f627ad4549dfe3ab8c0bf70af5afcde551b/onnxruntime-1.24.4-cp312-cp312-win_arm64.whl", hash = "sha256:e6214096e14b7b52e3bee1903dc12dc7ca09cb65e26664668a4620cc5e6f9a90", size = 12270275, upload-time = "2026-03-17T22:05:31.132Z" },
|
||||
{ url = "https://pypi.tuna.tsinghua.edu.cn/packages/e9/f0/8a21ec0a97e40abb7d8da1e8b20fb9e1af509cc6d191f6faa75f73622fb2/onnxruntime-1.24.4-cp313-cp313-macosx_14_0_arm64.whl", hash = "sha256:e99a48078baaefa2b50fe5836c319499f71f13f76ed32d0211f39109147a49e0", size = 17341922, upload-time = "2026-03-17T22:03:56.364Z" },
|
||||
{ url = "https://pypi.tuna.tsinghua.edu.cn/packages/8b/25/d7908de8e08cee9abfa15b8aa82349b79733ae5865162a3609c11598805d/onnxruntime-1.24.4-cp313-cp313-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:dc4aaed1e5e1aaacf2343c838a30a7c3ade78f13eeb16817411f929d04040a13", size = 15172290, upload-time = "2026-03-17T22:03:37.124Z" },
|
||||
{ url = "https://pypi.tuna.tsinghua.edu.cn/packages/7f/72/105ec27a78c5aa0154a7c0cd8c41c19a97799c3b12fc30392928997e3be3/onnxruntime-1.24.4-cp313-cp313-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:e30c972bc02e072911aabb6891453ec73795386c0af2b761b65444b8a4c4745f", size = 17244738, upload-time = "2026-03-17T22:04:40.625Z" },
|
||||
{ url = "https://pypi.tuna.tsinghua.edu.cn/packages/05/fb/a592736d968c2f58e12de4d52088dda8e0e724b26ad5c0487263adb45875/onnxruntime-1.24.4-cp313-cp313-win_amd64.whl", hash = "sha256:3b6ba8b0181a3aa88edab00eb01424ffc06f42e71095a91186c2249415fcff93", size = 12597435, upload-time = "2026-03-17T22:05:43.826Z" },
|
||||
{ url = "https://pypi.tuna.tsinghua.edu.cn/packages/ad/04/ae2479e9841b64bd2eb44f8a64756c62593f896514369a11243b1b86ca5c/onnxruntime-1.24.4-cp313-cp313-win_arm64.whl", hash = "sha256:71d6a5c1821d6e8586a024000ece458db8f2fc0ecd050435d45794827ce81e19", size = 12269852, upload-time = "2026-03-17T22:05:33.353Z" },
|
||||
{ url = "https://pypi.tuna.tsinghua.edu.cn/packages/b4/af/a479a536c4398ffaf49fbbe755f45d5b8726bdb4335ab31b537f3d7149b8/onnxruntime-1.24.4-cp313-cp313t-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:1700f559c8086d06b2a4d5de51e62cb4ff5e2631822f71a36db8c72383db71ee", size = 15176861, upload-time = "2026-03-17T22:03:40.143Z" },
|
||||
{ url = "https://pypi.tuna.tsinghua.edu.cn/packages/be/13/19f5da70c346a76037da2c2851ecbf1266e61d7f0dcdb887c667210d4608/onnxruntime-1.24.4-cp313-cp313t-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:4c74e268dc808e61e63784d43f9ddcdaf50a776c2819e8bd1d1b11ef64bf7e36", size = 17247454, upload-time = "2026-03-17T22:04:46.643Z" },
|
||||
{ url = "https://pypi.tuna.tsinghua.edu.cn/packages/81/b1/d111b1df656761f980d9e298a60039a9cb66036b1d039e777537743d0ac3/onnxruntime-1.26.0-cp312-cp312-macosx_14_0_arm64.whl", hash = "sha256:05b028781b322ad74b57ce5b50aa5280bb1fe96ceec334628ade681e0b24c1ac", size = 18016624, upload-time = "2026-05-12T00:41:01.735Z" },
|
||||
{ url = "https://pypi.tuna.tsinghua.edu.cn/packages/f6/a0/3f9d896a0385a36bd04345d6d0b802821a5782adde562e7e135f6bb71c73/onnxruntime-1.26.0-cp312-cp312-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:91f2bb870a4b9224eba0a6728c1fa7a9e552b8e59e1083c51fbbc3d013f2b5c0", size = 16052692, upload-time = "2026-05-08T19:07:13.829Z" },
|
||||
{ url = "https://pypi.tuna.tsinghua.edu.cn/packages/7c/43/2a4e04f8dbeffad19bbcced4bcd4289bf478921518437404d6b92bdf213b/onnxruntime-1.26.0-cp312-cp312-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:9b6dd70599005bd1bf29779f04a91978b92b5e719c11a20068a8f8e535f725b6", size = 18185439, upload-time = "2026-05-08T19:07:36.299Z" },
|
||||
{ url = "https://pypi.tuna.tsinghua.edu.cn/packages/44/fc/026d0a7162b9c2153dac292baea9e027c42304dc1d9dc6f8ff5b4cfbaedd/onnxruntime-1.26.0-cp312-cp312-win_amd64.whl", hash = "sha256:a26374dc7fbcaae593601086b242120e13f2310558df0991da6dd8b8fac00414", size = 13026427, upload-time = "2026-05-08T19:08:03.503Z" },
|
||||
{ url = "https://pypi.tuna.tsinghua.edu.cn/packages/3e/27/1dcf88e45e4c69db5f7b106f2dacc3801ba98994e082ca03e1dfdf7bfe57/onnxruntime-1.26.0-cp312-cp312-win_arm64.whl", hash = "sha256:54a8053410fd31fd66469bd754fcfe8a4df9f7eb44756b4b5479bf50c842d948", size = 12796647, upload-time = "2026-05-08T19:07:52.108Z" },
|
||||
{ url = "https://pypi.tuna.tsinghua.edu.cn/packages/cf/a2/c801242685e0ce48a4ca51dfafbb588765e0446397e123be53ba5598f3f5/onnxruntime-1.26.0-cp313-cp313-macosx_14_0_arm64.whl", hash = "sha256:ccce19c5f771b8268902f77d9fed9e88f9499465d6780808faa6611a789d33f0", size = 18016563, upload-time = "2026-05-08T19:07:28.081Z" },
|
||||
{ url = "https://pypi.tuna.tsinghua.edu.cn/packages/e2/64/0492c0b1db04e29b2630c87cfa36f9d6872b1ca8614b90c5cad58fac7d76/onnxruntime-1.26.0-cp313-cp313-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:bdbed8cf3b672b66acb032f33a253bc27f42bce6ece48ae3fab4fa483a5e96e0", size = 16052634, upload-time = "2026-05-08T19:07:16.885Z" },
|
||||
{ url = "https://pypi.tuna.tsinghua.edu.cn/packages/3d/26/4d09ddc755a84fc8d5e192991626b0e0680e8f6c5d58f4f1d05c42bc48cf/onnxruntime-1.26.0-cp313-cp313-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:c07af6fc6d5557835f2b6ee7a96d8b3235d0c57a8e230efdedaee106a8a3cbc6", size = 18185632, upload-time = "2026-05-08T19:07:38.756Z" },
|
||||
{ url = "https://pypi.tuna.tsinghua.edu.cn/packages/77/89/3e52249aa08fa301e217ecba07b5246a8338fa2b401e109326e3fc5be0f9/onnxruntime-1.26.0-cp313-cp313-win_amd64.whl", hash = "sha256:61bec80655efa460591c2bc655392d57d2650ce85533a6b9b3b7a790d7ea7916", size = 13026751, upload-time = "2026-05-08T19:08:06.2Z" },
|
||||
{ url = "https://pypi.tuna.tsinghua.edu.cn/packages/06/b3/c1c8782b14af6797c303de132d6eef26a9fb80dfacd3750ce57911d11c6b/onnxruntime-1.26.0-cp313-cp313-win_arm64.whl", hash = "sha256:a6677545ff451e3539a02746d2f207d8c5baa4a0a818886bb9d6a6eb9511ee89", size = 12796807, upload-time = "2026-05-08T19:07:54.879Z" },
|
||||
{ url = "https://pypi.tuna.tsinghua.edu.cn/packages/c3/f5/47b0676408abec652c14b84d7173e389837832d850c24f87184277313e8d/onnxruntime-1.26.0-cp313-cp313t-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:5e016edc15d3c19f36807e1c6b10be5b27807688c32720f91b5ae480a95215d0", size = 16057265, upload-time = "2026-05-08T19:07:19.603Z" },
|
||||
{ url = "https://pypi.tuna.tsinghua.edu.cn/packages/3b/45/33ab6deeef010ca844c877dd618cebc079590bbe52d2a3678e7223b1b908/onnxruntime-1.26.0-cp313-cp313t-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:f5fc48a91a046a6a5c9b147f83fb41d65d24d24923373b222cdd248f0f4f4aac", size = 18197590, upload-time = "2026-05-08T19:07:41.422Z" },
|
||||
]
|
||||
|
||||
[[package]]
|
||||
@ -4042,25 +4041,6 @@ wheels = [
|
||||
{ url = "https://pypi.tuna.tsinghua.edu.cn/packages/5c/b8/011338eec8aea40cf9b82da7481f3e65e100537cff4c866b3c1b1e719b97/rapidocr-3.7.0-py3-none-any.whl", hash = "sha256:ace47f037956fa3780875f8556a0f27ab20d91962d36a9a2816aa367bb48718f", size = 15080131, upload-time = "2026-03-04T15:38:20.339Z" },
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "rapidocr-onnxruntime"
|
||||
version = "1.4.4"
|
||||
source = { registry = "https://pypi.tuna.tsinghua.edu.cn/simple" }
|
||||
dependencies = [
|
||||
{ name = "numpy" },
|
||||
{ name = "onnxruntime" },
|
||||
{ name = "opencv-python" },
|
||||
{ name = "pillow" },
|
||||
{ name = "pyclipper" },
|
||||
{ name = "pyyaml" },
|
||||
{ name = "shapely" },
|
||||
{ name = "six" },
|
||||
{ name = "tqdm" },
|
||||
]
|
||||
wheels = [
|
||||
{ url = "https://pypi.tuna.tsinghua.edu.cn/packages/ba/12/1e5497183bdbe782dbb91bad1d0d2297dba4d2831b2652657f7517bfc6df/rapidocr_onnxruntime-1.4.4-py3-none-any.whl", hash = "sha256:971d7d5f223a7a808662229df1ef69893809d8457d834e6373d3854bc1782cbf", size = 14915192, upload-time = "2025-01-17T01:48:25.104Z" },
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "readability-lxml"
|
||||
version = "0.8.4.1"
|
||||
@ -4931,9 +4911,9 @@ dependencies = [
|
||||
{ name = "typing-extensions", marker = "sys_platform == 'darwin'" },
|
||||
]
|
||||
wheels = [
|
||||
{ url = "https://download-r2.pytorch.org/whl/cpu/torch-2.8.0-cp312-none-macosx_11_0_arm64.whl", hash = "sha256:a47b7986bee3f61ad217d8a8ce24605809ab425baf349f97de758815edd2ef54" },
|
||||
{ url = "https://download-r2.pytorch.org/whl/cpu/torch-2.8.0-cp313-cp313t-macosx_14_0_arm64.whl", hash = "sha256:fbe2e149c5174ef90d29a5f84a554dfaf28e003cb4f61fa2c8c024c17ec7ca58" },
|
||||
{ url = "https://download-r2.pytorch.org/whl/cpu/torch-2.8.0-cp313-none-macosx_11_0_arm64.whl", hash = "sha256:057efd30a6778d2ee5e2374cd63a63f63311aa6f33321e627c655df60abdd390" },
|
||||
{ url = "https://download-r2.pytorch.org/whl/cpu/torch-2.8.0-cp312-none-macosx_11_0_arm64.whl", hash = "sha256:a47b7986bee3f61ad217d8a8ce24605809ab425baf349f97de758815edd2ef54", upload-time = "2025-10-01T23:35:50Z" },
|
||||
{ url = "https://download-r2.pytorch.org/whl/cpu/torch-2.8.0-cp313-cp313t-macosx_14_0_arm64.whl", hash = "sha256:fbe2e149c5174ef90d29a5f84a554dfaf28e003cb4f61fa2c8c024c17ec7ca58", upload-time = "2025-10-01T23:35:52Z" },
|
||||
{ url = "https://download-r2.pytorch.org/whl/cpu/torch-2.8.0-cp313-none-macosx_11_0_arm64.whl", hash = "sha256:057efd30a6778d2ee5e2374cd63a63f63311aa6f33321e627c655df60abdd390", upload-time = "2025-10-01T23:35:55Z" },
|
||||
]
|
||||
|
||||
[[package]]
|
||||
@ -4956,19 +4936,19 @@ dependencies = [
|
||||
{ name = "typing-extensions", marker = "sys_platform != 'darwin'" },
|
||||
]
|
||||
wheels = [
|
||||
{ url = "https://download-r2.pytorch.org/whl/cpu/torch-2.8.0%2Bcpu-cp312-cp312-linux_s390x.whl", hash = "sha256:0e34e276722ab7dd0dffa9e12fe2135a9b34a0e300c456ed7ad6430229404eb5" },
|
||||
{ url = "https://download-r2.pytorch.org/whl/cpu/torch-2.8.0%2Bcpu-cp312-cp312-manylinux_2_28_aarch64.whl", hash = "sha256:610f600c102386e581327d5efc18c0d6edecb9820b4140d26163354a99cd800d" },
|
||||
{ url = "https://download-r2.pytorch.org/whl/cpu/torch-2.8.0%2Bcpu-cp312-cp312-manylinux_2_28_x86_64.whl", hash = "sha256:cb9a8ba8137ab24e36bf1742cb79a1294bd374db570f09fc15a5e1318160db4e" },
|
||||
{ url = "https://download-r2.pytorch.org/whl/cpu/torch-2.8.0%2Bcpu-cp312-cp312-win_amd64.whl", hash = "sha256:2be20b2c05a0cce10430cc25f32b689259640d273232b2de357c35729132256d" },
|
||||
{ url = "https://download-r2.pytorch.org/whl/cpu/torch-2.8.0%2Bcpu-cp312-cp312-win_arm64.whl", hash = "sha256:99fc421a5d234580e45957a7b02effbf3e1c884a5dd077afc85352c77bf41434" },
|
||||
{ url = "https://download-r2.pytorch.org/whl/cpu/torch-2.8.0%2Bcpu-cp313-cp313-linux_s390x.whl", hash = "sha256:8b5882276633cf91fe3d2d7246c743b94d44a7e660b27f1308007fdb1bb89f7d" },
|
||||
{ url = "https://download-r2.pytorch.org/whl/cpu/torch-2.8.0%2Bcpu-cp313-cp313-manylinux_2_28_aarch64.whl", hash = "sha256:a5064b5e23772c8d164068cc7c12e01a75faf7b948ecd95a0d4007d7487e5f25" },
|
||||
{ url = "https://download-r2.pytorch.org/whl/cpu/torch-2.8.0%2Bcpu-cp313-cp313-manylinux_2_28_x86_64.whl", hash = "sha256:8f81dedb4c6076ec325acc3b47525f9c550e5284a18eae1d9061c543f7b6e7de" },
|
||||
{ url = "https://download-r2.pytorch.org/whl/cpu/torch-2.8.0%2Bcpu-cp313-cp313-win_amd64.whl", hash = "sha256:e1ee1b2346ade3ea90306dfbec7e8ff17bc220d344109d189ae09078333b0856" },
|
||||
{ url = "https://download-r2.pytorch.org/whl/cpu/torch-2.8.0%2Bcpu-cp313-cp313-win_arm64.whl", hash = "sha256:64c187345509f2b1bb334feed4666e2c781ca381874bde589182f81247e61f88" },
|
||||
{ url = "https://download-r2.pytorch.org/whl/cpu/torch-2.8.0%2Bcpu-cp313-cp313t-manylinux_2_28_aarch64.whl", hash = "sha256:af81283ac671f434b1b25c95ba295f270e72db1fad48831eb5e4748ff9840041" },
|
||||
{ url = "https://download-r2.pytorch.org/whl/cpu/torch-2.8.0%2Bcpu-cp313-cp313t-manylinux_2_28_x86_64.whl", hash = "sha256:a9dbb6f64f63258bc811e2c0c99640a81e5af93c531ad96e95c5ec777ea46dab" },
|
||||
{ url = "https://download-r2.pytorch.org/whl/cpu/torch-2.8.0%2Bcpu-cp313-cp313t-win_amd64.whl", hash = "sha256:6d93a7165419bc4b2b907e859ccab0dea5deeab261448ae9a5ec5431f14c0e64" },
|
||||
{ url = "https://download-r2.pytorch.org/whl/cpu/torch-2.8.0%2Bcpu-cp312-cp312-linux_s390x.whl", hash = "sha256:0e34e276722ab7dd0dffa9e12fe2135a9b34a0e300c456ed7ad6430229404eb5", upload-time = "2025-10-01T23:33:41Z" },
|
||||
{ url = "https://download-r2.pytorch.org/whl/cpu/torch-2.8.0%2Bcpu-cp312-cp312-manylinux_2_28_aarch64.whl", hash = "sha256:610f600c102386e581327d5efc18c0d6edecb9820b4140d26163354a99cd800d", upload-time = "2025-10-01T23:33:45Z" },
|
||||
{ url = "https://download-r2.pytorch.org/whl/cpu/torch-2.8.0%2Bcpu-cp312-cp312-manylinux_2_28_x86_64.whl", hash = "sha256:cb9a8ba8137ab24e36bf1742cb79a1294bd374db570f09fc15a5e1318160db4e", upload-time = "2025-10-01T23:33:48Z" },
|
||||
{ url = "https://download-r2.pytorch.org/whl/cpu/torch-2.8.0%2Bcpu-cp312-cp312-win_amd64.whl", hash = "sha256:2be20b2c05a0cce10430cc25f32b689259640d273232b2de357c35729132256d", upload-time = "2025-10-01T23:33:52Z" },
|
||||
{ url = "https://download-r2.pytorch.org/whl/cpu/torch-2.8.0%2Bcpu-cp312-cp312-win_arm64.whl", hash = "sha256:99fc421a5d234580e45957a7b02effbf3e1c884a5dd077afc85352c77bf41434", upload-time = "2025-10-01T23:34:10Z" },
|
||||
{ url = "https://download-r2.pytorch.org/whl/cpu/torch-2.8.0%2Bcpu-cp313-cp313-linux_s390x.whl", hash = "sha256:8b5882276633cf91fe3d2d7246c743b94d44a7e660b27f1308007fdb1bb89f7d", upload-time = "2025-10-01T23:34:15Z" },
|
||||
{ url = "https://download-r2.pytorch.org/whl/cpu/torch-2.8.0%2Bcpu-cp313-cp313-manylinux_2_28_aarch64.whl", hash = "sha256:a5064b5e23772c8d164068cc7c12e01a75faf7b948ecd95a0d4007d7487e5f25", upload-time = "2025-10-01T23:34:19Z" },
|
||||
{ url = "https://download-r2.pytorch.org/whl/cpu/torch-2.8.0%2Bcpu-cp313-cp313-manylinux_2_28_x86_64.whl", hash = "sha256:8f81dedb4c6076ec325acc3b47525f9c550e5284a18eae1d9061c543f7b6e7de", upload-time = "2025-10-01T23:34:23Z" },
|
||||
{ url = "https://download-r2.pytorch.org/whl/cpu/torch-2.8.0%2Bcpu-cp313-cp313-win_amd64.whl", hash = "sha256:e1ee1b2346ade3ea90306dfbec7e8ff17bc220d344109d189ae09078333b0856", upload-time = "2025-10-01T23:34:28Z" },
|
||||
{ url = "https://download-r2.pytorch.org/whl/cpu/torch-2.8.0%2Bcpu-cp313-cp313-win_arm64.whl", hash = "sha256:64c187345509f2b1bb334feed4666e2c781ca381874bde589182f81247e61f88", upload-time = "2025-10-01T23:34:45Z" },
|
||||
{ url = "https://download-r2.pytorch.org/whl/cpu/torch-2.8.0%2Bcpu-cp313-cp313t-manylinux_2_28_aarch64.whl", hash = "sha256:af81283ac671f434b1b25c95ba295f270e72db1fad48831eb5e4748ff9840041", upload-time = "2025-10-01T23:34:50Z" },
|
||||
{ url = "https://download-r2.pytorch.org/whl/cpu/torch-2.8.0%2Bcpu-cp313-cp313t-manylinux_2_28_x86_64.whl", hash = "sha256:a9dbb6f64f63258bc811e2c0c99640a81e5af93c531ad96e95c5ec777ea46dab", upload-time = "2025-10-01T23:34:53Z" },
|
||||
{ url = "https://download-r2.pytorch.org/whl/cpu/torch-2.8.0%2Bcpu-cp313-cp313t-win_amd64.whl", hash = "sha256:6d93a7165419bc4b2b907e859ccab0dea5deeab261448ae9a5ec5431f14c0e64", upload-time = "2025-10-01T23:34:58Z" },
|
||||
]
|
||||
|
||||
[[package]]
|
||||
@ -4988,12 +4968,12 @@ dependencies = [
|
||||
{ name = "torch", version = "2.8.0+cpu", source = { registry = "https://download.pytorch.org/whl/cpu" }, marker = "platform_machine == 'aarch64' and platform_python_implementation == 'CPython' and sys_platform == 'linux'" },
|
||||
]
|
||||
wheels = [
|
||||
{ url = "https://download-r2.pytorch.org/whl/cpu/torchvision-0.23.0-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:e0e2c04a91403e8dd3af9756c6a024a1d9c0ed9c0d592a8314ded8f4fe30d440" },
|
||||
{ url = "https://download-r2.pytorch.org/whl/cpu/torchvision-0.23.0-cp312-cp312-manylinux_2_28_aarch64.whl", hash = "sha256:6dd7c4d329a0e03157803031bc856220c6155ef08c26d4f5bbac938acecf0948" },
|
||||
{ url = "https://download-r2.pytorch.org/whl/cpu/torchvision-0.23.0-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:1c37e325e09a184b730c3ef51424f383ec5745378dc0eca244520aca29722600" },
|
||||
{ url = "https://download-r2.pytorch.org/whl/cpu/torchvision-0.23.0-cp313-cp313-manylinux_2_28_aarch64.whl", hash = "sha256:2f7fd6c15f3697e80627b77934f77705f3bc0e98278b989b2655de01f6903e1d" },
|
||||
{ url = "https://download-r2.pytorch.org/whl/cpu/torchvision-0.23.0-cp313-cp313t-macosx_11_0_arm64.whl", hash = "sha256:2df618e1143805a7673aaf82cb5720dd9112d4e771983156aaf2ffff692eebf9" },
|
||||
{ url = "https://download-r2.pytorch.org/whl/cpu/torchvision-0.23.0-cp313-cp313t-manylinux_2_28_aarch64.whl", hash = "sha256:2a3299d2b1d5a7aed2d3b6ffb69c672ca8830671967eb1cee1497bacd82fe47b" },
|
||||
{ url = "https://download-r2.pytorch.org/whl/cpu/torchvision-0.23.0-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:e0e2c04a91403e8dd3af9756c6a024a1d9c0ed9c0d592a8314ded8f4fe30d440", upload-time = "2025-08-05T20:11:47Z" },
|
||||
{ url = "https://download-r2.pytorch.org/whl/cpu/torchvision-0.23.0-cp312-cp312-manylinux_2_28_aarch64.whl", hash = "sha256:6dd7c4d329a0e03157803031bc856220c6155ef08c26d4f5bbac938acecf0948", upload-time = "2025-08-05T20:11:47Z" },
|
||||
{ url = "https://download-r2.pytorch.org/whl/cpu/torchvision-0.23.0-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:1c37e325e09a184b730c3ef51424f383ec5745378dc0eca244520aca29722600", upload-time = "2025-08-05T20:11:47Z" },
|
||||
{ url = "https://download-r2.pytorch.org/whl/cpu/torchvision-0.23.0-cp313-cp313-manylinux_2_28_aarch64.whl", hash = "sha256:2f7fd6c15f3697e80627b77934f77705f3bc0e98278b989b2655de01f6903e1d", upload-time = "2025-08-05T20:11:47Z" },
|
||||
{ url = "https://download-r2.pytorch.org/whl/cpu/torchvision-0.23.0-cp313-cp313t-macosx_11_0_arm64.whl", hash = "sha256:2df618e1143805a7673aaf82cb5720dd9112d4e771983156aaf2ffff692eebf9", upload-time = "2025-08-05T20:11:47Z" },
|
||||
{ url = "https://download-r2.pytorch.org/whl/cpu/torchvision-0.23.0-cp313-cp313t-manylinux_2_28_aarch64.whl", hash = "sha256:2a3299d2b1d5a7aed2d3b6ffb69c672ca8830671967eb1cee1497bacd82fe47b", upload-time = "2025-08-05T20:11:47Z" },
|
||||
]
|
||||
|
||||
[[package]]
|
||||
@ -5010,12 +4990,12 @@ dependencies = [
|
||||
{ name = "torch", version = "2.8.0+cpu", source = { registry = "https://download.pytorch.org/whl/cpu" }, marker = "(platform_machine != 'aarch64' and sys_platform == 'linux') or (platform_python_implementation != 'CPython' and sys_platform == 'linux') or (sys_platform != 'darwin' and sys_platform != 'linux')" },
|
||||
]
|
||||
wheels = [
|
||||
{ url = "https://download-r2.pytorch.org/whl/cpu/torchvision-0.23.0%2Bcpu-cp312-cp312-manylinux_2_28_x86_64.whl", hash = "sha256:ae459d4509d3b837b978dc6c66106601f916b6d2cda75c137e3f5f48324ce1da" },
|
||||
{ url = "https://download-r2.pytorch.org/whl/cpu/torchvision-0.23.0%2Bcpu-cp312-cp312-win_amd64.whl", hash = "sha256:a651ccc540cf4c87eb988730c59c2220c52b57adc276f044e7efb9830fa65a1d" },
|
||||
{ url = "https://download-r2.pytorch.org/whl/cpu/torchvision-0.23.0%2Bcpu-cp313-cp313-manylinux_2_28_x86_64.whl", hash = "sha256:dea90a67d60a5366b0358a0b8d6bf267805278697d6fd950cf0e31139e56d1be" },
|
||||
{ url = "https://download-r2.pytorch.org/whl/cpu/torchvision-0.23.0%2Bcpu-cp313-cp313-win_amd64.whl", hash = "sha256:82928788025170c62e7df1120dcdc0cd175bfc31c08374613ce6d1a040bc0cda" },
|
||||
{ url = "https://download-r2.pytorch.org/whl/cpu/torchvision-0.23.0%2Bcpu-cp313-cp313t-manylinux_2_28_x86_64.whl", hash = "sha256:474d77adbbbed5166db3e5636b4b4ae3399c66ef5bfa12536e254b32259c90c0" },
|
||||
{ url = "https://download-r2.pytorch.org/whl/cpu/torchvision-0.23.0%2Bcpu-cp313-cp313t-win_amd64.whl", hash = "sha256:8d6a47e23d7896f0ef9aa7ea7179eb6324e82438aa66d19884c2020d0646b104" },
|
||||
{ url = "https://download-r2.pytorch.org/whl/cpu/torchvision-0.23.0%2Bcpu-cp312-cp312-manylinux_2_28_x86_64.whl", hash = "sha256:ae459d4509d3b837b978dc6c66106601f916b6d2cda75c137e3f5f48324ce1da", upload-time = "2025-08-05T20:11:47Z" },
|
||||
{ url = "https://download-r2.pytorch.org/whl/cpu/torchvision-0.23.0%2Bcpu-cp312-cp312-win_amd64.whl", hash = "sha256:a651ccc540cf4c87eb988730c59c2220c52b57adc276f044e7efb9830fa65a1d", upload-time = "2025-08-05T20:11:47Z" },
|
||||
{ url = "https://download-r2.pytorch.org/whl/cpu/torchvision-0.23.0%2Bcpu-cp313-cp313-manylinux_2_28_x86_64.whl", hash = "sha256:dea90a67d60a5366b0358a0b8d6bf267805278697d6fd950cf0e31139e56d1be", upload-time = "2025-08-05T20:11:47Z" },
|
||||
{ url = "https://download-r2.pytorch.org/whl/cpu/torchvision-0.23.0%2Bcpu-cp313-cp313-win_amd64.whl", hash = "sha256:82928788025170c62e7df1120dcdc0cd175bfc31c08374613ce6d1a040bc0cda", upload-time = "2025-08-05T20:11:47Z" },
|
||||
{ url = "https://download-r2.pytorch.org/whl/cpu/torchvision-0.23.0%2Bcpu-cp313-cp313t-manylinux_2_28_x86_64.whl", hash = "sha256:474d77adbbbed5166db3e5636b4b4ae3399c66ef5bfa12536e254b32259c90c0", upload-time = "2025-08-05T20:11:47Z" },
|
||||
{ url = "https://download-r2.pytorch.org/whl/cpu/torchvision-0.23.0%2Bcpu-cp313-cp313t-win_amd64.whl", hash = "sha256:8d6a47e23d7896f0ef9aa7ea7179eb6324e82438aa66d19884c2020d0646b104", upload-time = "2025-08-05T20:11:47Z" },
|
||||
]
|
||||
|
||||
[[package]]
|
||||
@ -5704,6 +5684,7 @@ dependencies = [
|
||||
{ name = "neo4j" },
|
||||
{ name = "networkx" },
|
||||
{ name = "nltk" },
|
||||
{ name = "onnxruntime" },
|
||||
{ name = "openai" },
|
||||
{ name = "opencv-python-headless" },
|
||||
{ name = "pillow" },
|
||||
@ -5717,7 +5698,7 @@ dependencies = [
|
||||
{ name = "python-jose", extra = ["cryptography"] },
|
||||
{ name = "python-multipart" },
|
||||
{ name = "pyyaml" },
|
||||
{ name = "rapidocr-onnxruntime" },
|
||||
{ name = "rapidocr" },
|
||||
{ name = "readability-lxml" },
|
||||
{ name = "redis" },
|
||||
{ name = "rich" },
|
||||
@ -5782,6 +5763,7 @@ requires-dist = [
|
||||
{ name = "neo4j", specifier = ">=5.28.1" },
|
||||
{ name = "networkx", specifier = ">=3.5" },
|
||||
{ name = "nltk", specifier = ">=3.8.1" },
|
||||
{ name = "onnxruntime", specifier = ">=1.20.0" },
|
||||
{ name = "openai", specifier = ">=1.109" },
|
||||
{ name = "opencv-python-headless", specifier = ">=4.11.0.86" },
|
||||
{ name = "pillow", specifier = ">=10.5.0" },
|
||||
@ -5795,7 +5777,7 @@ requires-dist = [
|
||||
{ name = "python-jose", extras = ["cryptography"], specifier = ">=3.4.0" },
|
||||
{ name = "python-multipart", specifier = ">=0.0.20" },
|
||||
{ name = "pyyaml", specifier = ">=6.0.2" },
|
||||
{ name = "rapidocr-onnxruntime", specifier = ">=1.4.4" },
|
||||
{ name = "rapidocr", specifier = ">=3.0.0" },
|
||||
{ name = "readability-lxml", specifier = ">=0.8.1" },
|
||||
{ name = "redis", specifier = ">=5.2.0" },
|
||||
{ name = "rich", specifier = ">=13.7.1" },
|
||||
|
||||
@ -3,7 +3,6 @@ x-api-worker-env: &api-worker-env
|
||||
LITE_MODE: ${LITE_MODE:-}
|
||||
RUNNING_IN_DOCKER: "true"
|
||||
YUXI_ENV: production
|
||||
MODEL_DIR_IN_DOCKER: /app/models
|
||||
PYTHONPATH: /app/package
|
||||
POSTGRES_URL: ${POSTGRES_URL:-postgresql+asyncpg://${POSTGRES_USER:-postgres}:${POSTGRES_PASSWORD:-postgres}@postgres:5432/${POSTGRES_DB:-yuxi_know}}
|
||||
REDIS_URL: ${REDIS_URL:-redis://redis:6379/0}
|
||||
|
||||
@ -3,7 +3,6 @@ x-api-worker-env: &api-worker-env
|
||||
LITE_MODE: ${LITE_MODE:-false}
|
||||
RUNNING_IN_DOCKER: "true"
|
||||
YUXI_ENV: development
|
||||
MODEL_DIR_IN_DOCKER: /models
|
||||
# DBs and other services
|
||||
POSTGRES_URL: ${POSTGRES_URL:-postgresql+asyncpg://${POSTGRES_USER:-postgres}:${POSTGRES_PASSWORD:-postgres}@postgres:5432/${POSTGRES_DB:-yuxi_know}}
|
||||
REDIS_URL: ${REDIS_URL:-redis://redis:6379/0}
|
||||
|
||||
@ -61,18 +61,9 @@ Yuxi 支持多种文档格式的智能解析，从简单的文本文件到复杂
|
||||
|
||||
## 快速配置
|
||||
|
||||
### RapidOCR（推荐入门）
|
||||
### RapidOCR
|
||||
|
||||
```bash
|
||||
# 下载模型
|
||||
hf download SWHL/RapidOCR --local-dir ./models/SWHL/RapidOCR
|
||||
|
||||
# 配置环境变量
|
||||
MODEL_DIR=./models
|
||||
|
||||
# 启动服务
|
||||
docker compose up -d api
|
||||
```
|
||||
启动后会默认下载，无需配置
|
||||
|
||||
### MinerU（高精度）
|
||||
|
||||
|
||||
Loading…
Reference in New Issue
Block a user